Explainable Text-Based Depression and Suicide Risk Prediction from Social Media Using Deep Learning and Graph Neural Networks. [PDF]
Rehman AU +5 more
europepmc +1 more source
ABSTRACT The human body functions as a natural reactor for a vast network of chemical and biological reactions and physical interactions among small molecules, proteins, cells, and numerous other components. These reactions/interactions are essential for maintaining normal physiological functions.
Yuhao Cai, Chao Zhao
wiley +1 more source
Temporal social network modeling of mobile connectivity data with graph neural networks. [PDF]
Jaskari J +5 more
europepmc +1 more source
We establish a tBid‐mediated cell ablation system in axolotls, achieve rapid and efficient ablation of multiple cell types, including muscle stem cell, spinal cord cell, and connective tissue (CT) cells. We investigate the role of CT using tBid‐mediated CT ablation and identify its essential role for limb development and regeneration.
Yan Hu +11 more
wiley +1 more source
Knowledge-based question answering using graph neural networks and contextual language representations. [PDF]
Samir M, Fathy N, Gad W.
europepmc +1 more source
MGDP: Mastering a Generalized Depth Perception Model for Quadruped Locomotion
ABSTRACT Perception‐based Deep Reinforcement Learning (DRL) controllers demonstrate impressive performance on challenging terrains. However, existing controllers still face core limitations, struggling to achieve both terrain generality and platform transferability, and are constrained by high computational overhead and sensitivity to sensor noise.
Yinzhao Dong +9 more
wiley +1 more source
Multilabel feature selection using graph neural networks and differential evolution optimization. [PDF]
Pan N.
europepmc +1 more source
Efficient Screening of Organic Singlet Fission Molecules Using Graph Neural Networks
A high‐throughput screening framework based on graph neural networks (GNNs) and multi‐level validation facilitates the identification of singlet fission (SF) candidates. By efficiently predicting excitation energies across 20 million molecules, and integrating TDDFT calculations, synthetic accessibility assessments, and GW+BSE calculations, this ...
Li Fu +5 more
wiley +1 more source
xGNN4MI: explainability of graph neural networks in 12-lead electrocardiography for cardiovascular disease classification. [PDF]
Maurer MC +7 more
europepmc +1 more source
Friend, Not Foe: Lowered Tissue Reactivity to Long‐Term Polyimide Implants
The choice of optimal neural probe designs remains a major challenge in the field of neurotechnology. This study investigated the biocompatibility of several probe variations, including material, thickness, width, and implantation strategy. It highlights the clear advantage of soft polyimide probes over stiff silicon probes for better device ...
Corinne Orlemann +11 more
wiley +1 more source

